Style transfer is a hot research topic in the field of image processing in recent years, but the current studies on style transfer mainly focus on the oil paintings, landscape paintings and other images. This paper extends the study of style transfer to the calligraphy fonts, and proposes a method based on generative adversarial networks (GAN). It uses GAN to learn the mapping between two training sets (i.e., Chinese famous calligraphy fonts and printed fonts), and then any calligraphy fonts

more »

... be automatically generated. In our experiments, the Wang Xizhi's calligraphy fonts dataset is used to train the GAN, and the trained-well GAN automatically generates the corresponding calligraphy fonts with Wang Xizhi's style. The experimental results demonstrate the feasibility of the proposed method.